Browsing by Author "Karci, A."

Now showing 1 - 6 of 6

Çizge Benzerliǧi Yöntemi ile Doküman Siniflandirma
(Institute of Electrical and Electronics Engineers Inc., 2019) Uçkan, T.; Hark, C.; Seyyarer, E.; Ayata, F.; Karci, A.
The classification of the documents is at the beginning of the topics that are studied extensively today. Using text similarity, many areas are used, such as whether citations are quoted elsewhere or the information searched in search engines is fast and accurate. A variety of methods are used while looking for similarities between documents. Similarity measurements are made by two basic methods, word-based and sentence-based, during the comparison of several documents. While word-based similarity measurements are made, many distance measurement methods such as Jaccard, Dice, Cosine similarity are used. In this study, the paragraphs in different documents will be broken down by sentence basis and they will be represented by a graph, and a study will be done on the classification of the documents using Hamming distance measurements by XOR method of neighborhood matrices obtained from these documents. © 2018 IEEE.
Doǧal Dil İşleme Yaklaşimlari ile Yapisal Olmayan Dökümanlarin Benzerliǧi
(Institute of Electrical and Electronics Engineers Inc., 2017) Hark, C.; Seyyarer, A.; Uçkan, T.; Karci, A.
Unstructured document and archive stacks that are formed in the past years are growing in size faster these days and they need to be clarified with various methods. This increases the interest in natural language processing discipline day by day and makes it more popular. In this study, we've tried to calculate the similarities between document stacks, that no information is presented onbehalf of their similarities and are completely independent of each other. Text mining approaches have been utilized in order to calculate the similarities of non-structural documents given. For this purpose, the R programming language labels have been used to structure only text based documents stacks in order to make them proccessable and to determine their similiraties afterwards. © 2017 IEEE.
Graph-Based Suggestion for Text Summarization
(Institute of Electrical and Electronics Engineers Inc., 2019) Hark, C.; Uçkan, T.; Seyyarer, E.; Karci, A.
One of the methods of text summarization within the context of Natural Language Processing (NLP) works is to summarize the text by selecting sentences from the original text. There are different approaches to summarize sentence selection. In this study, texts that do not have a certain structure have been preprocessed and transfer of the proposed diagram in a structured format in the form of an expression. Different feature extraction methods could be applied on the charts. Our method uses conceptually the diagrams obtained in the representation of the text. This study aims to suggest a method of summarization of texts with a linear weighting of the importance of sentences. Moreover, the method presented does not require the use of deep linguistic knowledge and this work can be adapted to different languages. © 2018 IEEE.
A Novel Approach for Image Compression Based on Multi-Level Image Thresholding Using Discrete Wavelet Transform and Cricket Algorithm
(Institute of Electrical and Electronics Engineers Inc., 2015) Canayaz, M.; Karci, A.
Applications of image compression is important in terms of time and resource management considering factors such as require more time to send according to the size of image over the network and large amount of space is high dimensional data for storing images. In this study, a new approach can be using at image compression process will be introduced. Firstly, image subjected to discrete wavelet transform for extracting feature. Then multi-level threshold values will be find with Shanon entropy in the obtained image. The maximum value of objective function will be obtained with the help of cricket algorithm at the threshold values finding step. This algorithm is a meta-heuristic algorithm that based on population. The threshold values that obtained through algorithm using to compressing the images will be provided. At the end of the study, the image compression ratio, the proposed approach running on a standard test image will be given. © 2015 IEEE.
A Novel Routing Protocol Based on Em-L Algorithm for Energy Efficiency of Wireless Sensor Networks
(Institute of Electrical and Electronics Engineers Inc., 2015) Özdaʇ, R.; Karci, A.
Wireless Sensor Networks (WSNs) make it possible to monitor a variety of environments in both civilian and military applications. Therefore, design and development of energy efficiency routing of WSNs has been formed an active research area until now. Because of sensors in the environment have a limited energy; their energy consumption has a vital importance for WSNs. Due to this reason in this study, It has been designed a new routing protocol utilizing random placement of dynamic cluster based stations (cluster head) to distribute the energy load among the sensors in the network equally. It has been developed the routing protocol based on Electromagnetism- Like (EM-L) which is a meta-heuristic algorithm, termed this protocol as 'Energy-Efficient Routing with EM-L Algorithm (E-EREM)' and applied to network in order to provide a routing energy efficient of cluster-based WSNs. Energy efficiency of the E-EREM protocol has been compared with LEACH (Low Energy Adaptive Clustering Hierarchy) algorithm. Simulation results demonstrated that using of the developed E-EREM protocol could be increased the lifetime of the network by optimizing the energy consumption of each sensor in the network. © 2015 IEEE.
Performance Comparisons of Optimization Algorithms
(Institute of Electrical and Electronics Engineers Inc., 2019) Inan, M.; Karaduman, M.; Karci, A.
Optimization methods are applied to many different problems. While these methods do not guarantee a definite end result, they give a solution that is close to the best result in a reasonable time. Optimization methods are classified as physical, social, music, herd, chemistry, biology and hybrid methods when classified according to the sources they are influenced by. In this study, it is aimed to compare the 5 methods of swarm optimization algorithm methods under the same conditions and applying the same probing. Thus, it is possible to determine the method that obtains the best values in terms of result and speed, and gives the fastest result. For this purpose, cat swarm optimization, whale swarm optimization, cricket algorithm, crow search optimization and salp optimization methods have been determined. When the result obtained from the comparison is evaluated, the best calculation time of the calculations for all functions is done with crow search optimization, the best results are obtained with whale swarm optimization for Ackley, salp optimization methods for Bukin N 6 and crow search optimization for Rastrigin. © 2018 IEEE.